Over-the-Air Adversarial Attacks on Deep Learning Based Modulation Classifier over Wireless Channels

Kim, Brian; Sagduyu, Yalin E.; Davaslıoğlu, Kemal; Erpek, Tugba; Ulukuş, Şennur

doi:10.1109/ciss48834.2020.1570617416

Cited by 74 publications

(44 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the multiple suggestions carried out towards assessing adversarial attacks have mainly focused on attacks targeting computer vision or object detection models. Few works have addressed adversarial learning in the wireless communications context [27][28][29][30]. Indeed, the latter presents certain specificities to be considered in the study of attacks targeting the models they employ.…”

Section: Related Workmentioning

confidence: 99%

“…In this context, an opponent can potentially introduce adversarial noise by employing multiple antennas to mislead the classifier and decrease its accuracy. They have demonstrated that using multiple antennas could enhance the opponent's attack robustness using a technique used in previous work [30] known as the maximum received perturbation power MRPP. They have evaluated this attack by emulating two different scenarios.…”

Section: ) Frequency Offsetmentioning

confidence: 99%

“…Afterwards, the attacker's potential and capabilities are analysed. Indeed, we have extensively detailed through Kim et al's [30] experience the impact of this factor in enhancing the robustness of the opponent's attack. In the previous section, we have already demonstrated that the adversary can improve the attack robustness by maximising the used antenna's power or increasing the number of antennas employed to carry out the adversarial attack.…”

Section: The Proposition Of Assessment Pattern Of Adversarial Attacks Robustness For Wireless Communicationmentioning

confidence: 99%

“…This disparity in assumptions provides a complex platform to make an accurate comparison of attacks on various algorithms. Since no unified scheme has been developed for assessing attacks robustness, we have proposed a framework to analyse and evaluate the robustness of adversarial attacks in the context of wireless communication [27][28][29][30]. This paper aims to provide a standardised and unified platform for comparing different adversarial attack strategies against wireless communication systems.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards Evaluating Adversarial Attacks Robustness in Wireless Communication

Ftaimi¹,

Mazri²

2021

IJACSA

View full text Add to dashboard Cite

The emerging new technologies, such as autonomous vehicles, augmented reality, IoT, and other aspects that are revolutionising our world today, have highlighted new requirements that wireless communications must fulfil. Wireless communications are expected to have a high optimisation capability, efficient detection ability, and prediction flexibility to meet today's cutting-edge telecommunications technologies' challenges and constraints. In this regard, the integration of deep learning models in wireless communications appears to be extremely promising. However, the study of deep learning models has exhibited inherent vulnerabilities that attackers could harness to compromise wireless communication systems. The examination of these vulnerabilities and the evaluation of the attacks leveraging them remains essential. Therefore, this paper's main objective is to address the alignment of security studies of deep learning models with wireless communications' specific requirements, thereby proposing a pattern for assessing adversarial attacks targeting deep learning models embedded in wireless communications.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: ) Frequency Offsetmentioning

confidence: 99%

Section: The Proposition Of Assessment Pattern Of Adversarial Attacks Robustness For Wireless Communicationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards Evaluating Adversarial Attacks Robustness in Wireless Communication

Ftaimi¹,

Mazri²

2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…Hence, the deep learning (DL) system wrongly uses these inputs to classify input signals [10,11]. These wrong classifications of signals are not "common white noise" but a distinct attribute in the feature space that leads to incorrect model outputs [12][13][14][15][16][17][18][19][20][21][22][23].…”

Section: Literature Reviewmentioning

confidence: 99%

Analysis of performance vulnerability of MAC scheduling algorithms due to SYN flood attack in 5G NR mmWave

Saikia¹,

Majumder²

2021

IJATEE

View full text Add to dashboard Cite

Fifth-generation (5G) new radio (NR) millimetre wave (mmWave) is a kind of 5G network that operates in the 24GHz to 100GHz frequency range. It offers several opportunities as well as numerous challenges. One of the most prominent challenges that a 5G network faces is intrusion. Intrusion is possible because of existing vulnerabilities in the 5G NR mmWave network architecture. We exploited one such vulnerabil ity to create synchronise (SYN) flood intrusion into the network. The SYN flood intrusion is a denial of service (DoS) intrusion. The intruder who is involved in the SYN flood intrusion depletes the network's available resources. As a result, it denies genuine UEs/nodes access to the network's services and resources. Since this attack produces many open connections with the server, it slows down media access control (MAC) schedulers' ability to assign available channels to the user equipment. In this article, we proposed a method to exploit existing vulnerabilities of the 5G NR mmWave network to carry out SYN flood attacks. Further, we investigated the effect of the attack on the performance of the MAC schedulers, such as proportionate fair and round robin MAC schedulers. With the addition of SYN flood attack UEs/nodes, we observed that the throughput for proportional fair and round robin MAC schedulers drops dramatically.In the event of an attack, throughput drops by 2.34 % to 37.7%. However, in the event of an SYN flood attack, network delay and jitter increase. The performance of the network suffers as a result of that.

show abstract